Xiwei Xu

SkillZip achieves a remarkable 3.46x compression ratio while preserving 99.2% of dependencies and 98.7% of verifier reachability, revolutionizing how agent skill libraries can be managed.

Brevis compresses tensor data by synthesizing a DSL program, achieving over 30% smaller archives than leading general-purpose compressors while ensuring bit-exact reconstruction.

SymCA achieves a remarkable balance between accuracy and interpretability in column annotation, outperforming traditional methods by over 6% in F1 scores.

Achieving stable and accurate alignment of generative 3D models with partial observations could redefine the standards for 3D reconstruction in computer vision.

Achieving human-level marking consistency, this LLM-as-Judge pipeline enhances educational assessments by grounding AI evaluations in official curriculum standards.

BioWeave enables smaller models to achieve reasoning performance on par with state-of-the-art LLMs, revolutionizing the landscape of biomedical question answering.

Run code LLMs 10x faster and with 6x less memory on your laptop without sacrificing accuracy, thanks to a new quantization and compilation approach.

Automating ESG reporting with LLM-powered agents transforms it from a static compliance exercise into a dynamic, data-driven system for sustainability governance.